BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Testing GPU Memory Consistency at Large - Reese Levine\, Universit
 y of California Santa Cruz
DTSTART:20240112T140000Z
DTEND:20240112T150000Z
UID:TALK210463@talks.cam.ac.uk
CONTACT:Jamie Vicary
DESCRIPTION:Memory consistency specifications (MCSs) are a difficult\, yet
  critical\, part of a concurrent programming framework. Existing MCS testi
 ng tools are not immediately accessible\, and thus\, have only been applie
 d to a limited number of devices. However\, in the post-Dennard scaling la
 ndscape\, there has been an explosion of new architectures and frameworks\
 , exemplified by graphics processing units (GPUs). Studying the shared mem
 ory semantics of these new platforms is important for understanding progra
 m behavior and ensuring conformance to framework specifications.\n\nIn thi
 s talk\, I will discuss our work on widescale GPU MCS testing. We develope
 d a new methodology\, MC Mutants\, which utilizes mutation testing to eval
 uate the effectiveness of MCS testing techniques. MC Mutants is built into
  an accessible testing tool\, GPUHarbor\, which we used to collect data fr
 om over 100 devices from seven GPU vendors. This massive testing campaign 
 revealed bugs in several GPU compilers and provided insights into weak beh
 avior characteristics across diverse architectures. Furthermore\, these re
 sults were used to tune testing environments across different devices\, al
 lowing us to make testing portable and contribute our tests to the officia
 l conformance test suite for WebGPU. Our ongoing work is investigating how
  to increase the safety and security of GPU programming languages in the f
 ace of their weak shared memory guarantees\, as well as the challenges and
  opportunities that come with evolving architectures.
LOCATION:SS03\, Computer Laboratory
END:VEVENT
END:VCALENDAR